Research

Below you can find a selection of preprints of academic handouts, papers, slides and essays on Natural Language Processing, Machine Learning & Theoretical Linguistics.

Theses

On the Potential for Maximising Minimal Means in Transformer Language Models

On the Potential for Maximising Minimal Means in Transformer Language Models
Suchir Salhan
BA Thesis

Less is More: Pre-Training Cross-Lingual Small-Scale Language Models with Cognitively-Plausible Curriculum Learning Strategies

Less is More: Pre-Training Cross-Lingual Small-Scale Language Models with Cognitively-Plausible Curriculum Learning Strategies
Suchir Salhan
MEng Thesis, published in the BabyLM Shared Task, co-located in EMNLP 2024

Conference & Journals Papers

Handouts

UROP Project Report 2021: Providing Automatic Feedback on Argumentation Quality to Learners of English

UROP Project Report 2021: Providing Automatic Feedback on Argumentation Quality to Learners of English
Suchir Salhan
Department of Computer Science & Technology, University of Cambridge

Multimodal Language Modelling across Languages and Cultures: Grounding Strategies for Concepts and Events

Multimodal Language Modelling across Languages and Cultures: Grounding Strategies for Concepts and Events
Suchir Salhan
Language Technology Lab, University of Cambridge